MCP tool for interactive feedback collection through Chrome extension with AI integration
16 tools with complete schemas and descriptions, but significant quality gaps. Tool names lack consistent verb-noun structure (chrome_interactive_feedback, chrome_get_feedback_history are inconsistent). Descriptions are present but generic (avg ~80 chars, below 194-char baseline). Parameters have types and descriptions, but many lack constraints (enums, ranges, patterns). No documented output schemas. Error handling is absent, no recovery guidance, no categorization of retryable vs fatal errors. Security concerns: chrome_execute_script accepts arbitrary JavaScript with no validation or sandboxing. No pagination support despite tools returning lists. Tool composition is poor, chrome_fill_form and chrome_interact_element overlap significantly.
Analyze form structure and provide intelligent field mapping suggestions
Clear all Chrome extension feedback history
Click on a DOM element using CSS selector
Execute JavaScript code in the current page
Extract content from page elements or get general page information
Intelligently fill out a form with multiple fields
Fill text into an input field
chrome_execute_script accepts arbitrary JavaScript with no validation, sandboxing, or safety guardrails. Agents can inject malicious code or break the browser state. No description of security implications or constraints.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields. E.g., chrome_get_feedback_history returns a list but no schema shows what fields each record contains.
Tool names lack consistent verb-noun structure. 'chrome_interactive_feedback' is a noun phrase; 'chrome_get_feedback_history' is verb-noun. Inconsistency confuses LLM tool selection. Should be 'chrome_request_feedback' or similar.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
Get Chrome extension connection status
Get history of collected feedback from Chrome extension
Get current page information (title, URL, DOM elements)
Perform various interactions with DOM elements (click, hover, select, etc.)
Request interactive feedback from user through Chrome extension interface
Navigate the current browser tab to a specific URL
Use Playwright-inspired smart element location strategies to find elements with high precision
Take a screenshot of the current page
Wait for an element to appear on the page
chrome_fill_form and chrome_interact_element overlap significantly, both manipulate DOM elements. chrome_interact_element supports 'select' and 'check' actions that duplicate chrome_fill_form. Composition is unclear; agents will struggle to choose between them.
No error handling or recovery guidance. Tools lack descriptions of failure modes, retryability, or what the LLM should do if a call fails. E.g., chrome_navigate_to_url may timeout or fail to load, no guidance on retry strategy or fallback.